Efficient implementation of OpenACC cache directive on NVIDIA GPUs
Bibliographic record
Abstract
OpenACC's programming model presents a simple interface to programmers, offering a trade-off between performance and development effort. OpenACC relies on compiler technologies to generate efficient code and optimise the performance. The cache directive is among the challenges to implement directives. The cache directive allows the programmer to utilise the accelerator's hardware- or software-managed caches by passing hints to the compiler. In this paper, we investigate the implementation aspect of cache directive under NVIDIA-like GPUs and propose optimisations for the CUDA backend. We use CUDA's shared memory as the software-managed cache space. We first show that a straightforward implementation can be very inefficient, and undesirably downgrade performance. We investigate the differences between this implementation and hand-written CUDA alternatives and introduce the following optimisations to bridge the performance gap between the two: 1) improving occupancy by sharing the cache among several parallel threads; 2) optimising cache fetch and write routines via parallelisation and minimising control flow. Investigating three test cases, we show that the best cache directive implementation can perform very close to hand-written CUDA equivalent and improve performance up to 2.4× (compared to the baseline OpenACC.)
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".